Using ML Methods for obtaining the prediction of maximum dry density

Ying  Liu; Liguo  Teng

doi:10.6180/jase.202605_29(5).0004

Using ML Methods for obtaining the prediction of maximum dry density

Environmental Engineering Water Resources Engineering

Ying Liu and Liguo TengThis email address is being protected from spambots. You need JavaScript enabled to view it.

Applied Technology College of Dalian Ocean University, Dalian 116300, China

Received: May 18, 2025
Accepted: July 30, 2025
Publication Date: August 25, 2025

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202605_29(5).0004

In geotechnical engineering, maximum dry density (MDD) is a fundamental concept, referring to the maximum mass per unit volume under specified conditions. MDD is pivotal for ensuring the stability of earthwork, including foundations and dams. It depends on factors like moisture, compaction force, grain size, and soil type. Accurate MDD prediction helps engineers ensure durability and reliability in civil engineering projects over time. This article, an original prediction method of MDD by means of the K-nearest neighbors (KNN) algorithm has been presented. Using the KNN method, accurate models can be developed that connect the MDD of treated soil to diverse natural soil attributes, including linear shrinkage, plasticity, particle size dispersion, and the type and content of stabilization additives. A large database comprising 187 samples representing various categories of soils from previously conducted stability tests has been utilized in this study to develop forecasting models and validate them. Besides, application of meta-heuristic strategies, specifically the Jellyfish Search Optimizer (JFO) and Black Widow Optimizing Algorithm (BWOA), further enhances the accuracy level of the KNN method in this work. Therefore, two hybrid models, KNJF and KNBW, are defined. Then, the data for the training, validation, and tests show excellent R2 values of 0.9895, 0.9681 and 0.9659, respectively, by the KNJF model. In addition, during the training phase KNJF has the best RMSE of 24.236. Everything taken into account, the KNJF model generalizes and predicts better than the models KNN and KNBW developed specifically for this investigation.

Keywords: K-nearest neighbor; Maximum Dry Density; Jellyfish Search Optimizer; Black Widow Optimization Algorithm(BWOA)

[1] Z.S. Janjua and J. Chand, (2016) “Correlation of CBR with index properties of soil" International Journal of Civil Engineering and Technology 7: 57–62.
[2] J. Duque, W. Fuentes, S. Rey, and E. Molina, (2020) “Effect of grain size distribution on california bearing ratio (CBR) and modified proctor parameters for granular mate rials" Arabian Journal for Science and Engineering 45: 8231–8239. DOI: https: //doi.org/10.1007/s13369-020-04673-6.
[3] M. Y. Khiabani, B. Sedaghat, P. Ghorbanzadeh, N. Porroustami, S. M. H. Shahdany, and Y. Hassani, (2023) “Application of a hybrid hydro-economic model to allocate water over the micro-and macro-scale region for enhancing socioeconomic criteria under the water shortage period" Water Econ Policy:
[4] S. Preethi, R. B. Tangadagi, M. Manjunatha, and A. Bharath, (2020) “Sustainable effect of chemically treated aggregates on bond strength of bitumen" J. Green Eng 10: 5076–5089.
[5] E. G. Akpokodje, (1985) “The stabilization of some arid zone soils with cement and lime" Quarterly journal of engineering geology 18: 173–180. DOI: https: //doi.org/10.1144/GSL.QJEG.1985.018.02.06.
[6] F. Bell, (1996) “Lime stabilization of clay minerals and soils" Engineering geology 42: 223–237. DOI: https: //doi.org/10.1016/0013-7952(96)00028-2.
[7] A. H. Alavi, A. H. Gandomi, M. Gandomi, and S. S. S. Hosseini, (2009) “Prediction of maximum dry density and optimum moisture content of stabilised soil using RBF neural networks" The IES Journal Part A: Civil Structural Engineering 2: 98–106. DOI: https: //doi.org/10.1080/19373260802659226.
[8] A.WorkuandD.Shiferaw, (2004) “Prediction of maximum dry density of local granular fills" Zede Journal 21: 59–70.
[9] A. B. Ngowi, (1997) “Improving the traditional earth construction: a case study of Botswana" Construction and Building Materials 11: 1–7. DOI: https: //doi.org/10.1016/S0950-0618(97)00006-8.
[10] C. KS, Y. M. Chew, M. H. Osman, and M. G. SK. “Estimating maximum dry density and optimum moisture content of compacted soils”. In: international conference on advances in civil and environmental engineer ing. 1. 2015, 8.
[11] A. Bharath, M. Manjunatha, T. V. Reshma, and S. Preethi, (2021) “Influence and correlation of maximum dry density on soaked unsoaked CBR of soil" Materials Today: Proceedings 47: 3998–4002. DOI: https: //doi.org/10.1016/j.matpr.2021.04.232.
[12] S. Suman, M. Mahamaya, and S. K. Das, (2016) “Pre diction of maximum dry density and unconfined com pressive strength of cement stabilised soil using artificial intelligence techniques" International Journal of Geosynthetics and Ground Engineering 2: 11. DOI: https: //doi.org/10.1007/s40891-016-0051-9.
[13] A. H. Alavi, A. H. Gandomi, A. Mollahassani, A. A. Heshmati, and A. Rashed, (2010) “Modeling of maximum dry density and optimum moisture content of stabilized soil using artificial neural networks" Journal of Plant Nutrition and Soil Science 173: 368–379. DOI: https: //doi.org/10.1002/jpln.200800233.
[14] F. Masoumi, S. Najjar-Ghabel, A. Safarzadeh, and B. Sadaghat, (2020) “Automatic calibration of the ground water simulation model with high parameter dimensionality using sequential uncertainty fitting approach" Water Supply20: 3487–3501. DOI: https: //doi.org/10.2166/ws.2020.241.
[15] H.F. H. Ali, (2023) “Utilizing multivariable mathematical models to predict maximum dry density and optimum moisture content from physical soil properties" Multi scale and Multidisciplinary Modeling, Experiments and Design 6: 603–627. DOI: https: //doi.org/10.1007/s41939-023-00165-w.
[16] H. Wang, Z. Lei, X. Zhang, B. Zhou, and J. Peng, (2016) “Machine learning basics" Deep learning: 98–164.
[17] B. Mahesh, (2020) “Machine Learning Algorithms—A Review" International Journal of Science and Re search 9: 381–386. DOI: http: //dx.doi.org/10.21275/ART20203995.
[18] Z.-H. Zhou. Machine learning. Springer nature, 2021. DOI: https: //doi.org/10.1007/978-981-15-1967-3.
[19] G. Biau, (2012) “Analysis of a random forests model" TheJournalofMachineLearningResearch13:1063–1095.
[20] K.-j. Kim, (2003) “Financial time series forecasting using support vector machines" Neurocomputing 55: 307 319. DOI: https: //doi.org/10.1016/S0925-2312(03)-00372-2.
[21] M. I. Jordan and T. M.Mitchell, (2015) “Machine learning: Trends, perspectives, and prospects" Science 349: 255–260. DOI: https: //doi.org/10.1126/science.aaa8415.
[22] B. Naeim, A. J. Khiavi, P. Dolatimehr, and B. Sadaghat, (2024) “Novel optimized support vector regression networks for estimating fresh and hardened characteristics of SCC" Advances in Engineering and Intelligence Systems 3: 110–123. DOI: https://doi.org/ 10.22034/aeis.2024.483317.1239.
[23] S. K. Das, P. Samui, and A. K. Sabat, (2011) “Appli cation of artificial intelligence to maximum dry density and unconfined compressive strength of cement stabilized soil" Geotechnical and Geological Engineering 29: 329–342. DOI: https: //doi.org/10.1007/s10706-010-9379-4.
[24] M. Saadat and M. Bayat, (2022) “Prediction of the un confined compressive strength of stabilised soil by Adaptive Neuro Fuzzy Inference System (ANFIS) and Non Linear Regression (NLR)" Geomechanics and Geo engineering 17: 80–91. DOI: https://doi.org/10.1080/17486025.2019.1699668.
[25] E. Kalkan, S. Akbulut, A. Tortum, and S. Celik, (2009) “Prediction of the unconfined compressive strength of compacted granular soils by using inference systems" Environmental geology 58: 1429–1440. DOI: https: //doi.org/10.1007/s00254-008-1645-x.
[26] G. G. Tejani, B. Sadaghat, and S. Kumar, (2023) “Predict the maximum dry density of soil based on individual and hybrid methods of machine learning" Advances in engineering and intelligence systems 2: 95–106. DOI: https: //doi.org/10.22034/aeis.2023.414188.1129.
[27] H. F. H. Ali, B. Omer, A. S. Mohammed, and R. H. Faraj, (2024) “Predicting the maximum dry density and optimum moisture content from soil index properties using efficient soft computing techniques" Neural Computing and Applications 36: 11339–11369. DOI: https: //doi.org/10.1007/s00521-024-09734-7.
[28] M.N.Duc,A.H.Sy,T.N.Ngoc,andT.L.H.Thi.“An artificial intelligence approach based on multi-layer perceptron neural network and random forest for predicting maximum dry density and optimum moisture content of soil material in quangninh province, vietnam”. In: CIGOS 2021, Emerging technologies and applications for green infrastructure: proceedings of the 6th international conference on geotechnics, civil engineering and structures. Springer, 2021, 1745–1754. DOI: https: //doi.org/10.1007/978-981-16-7160-9_176.
[29] M. Jia and Y. Zheng. “A prediction model of maximum dry density of over coarse-grained soil”. In: IOP Conference Series: Earth and Environmental Sci ence. 1330. IOP Publishing, 2024, 012050. DOI: https: //doi.org/10.1088/1755-1315/1330/1/012050.
[30] A. H. Alavi, A. H. Gandomi, and A. Mollahasani. “A genetic programming-based approach for the performance characteristics assessment of stabilized soil”. In: Springer, 2012, 343–376. DOI: https: //doi.org/10.1007/978-3-642-23424-8_11.
[31] W. Z. Taffese and K. A. Abegaz, (2022) “Prediction of compaction and strength properties of amended soil using machine learning" Buildings 12: 613. DOI: https: //doi.org/10.3390/buildings12050613.
[32] J.-S. Chou and D.-N. Truong, (2021) “A novel meta heuristic optimizer inspired by behavior of jellyfish in ocean" Applied Mathematics and Computation 389: 125535. DOI: https: //doi.org/10.1016/j.amc.2020.125535.
[33] A. M. Shaheen, R. A. El-Sehiemy, M. M. Alharthi, S. S. M. Ghoneim, and A. R. Ginidi, (2021) “Multi objective jellyfish search optimizer for efficient power system operation based on multi-dimensional OPF frame work" Energy 237: 121478. DOI: https: //doi.org/10.1016/j.energy.2021.121478.
[34] M. Farhat, S. Kamel, A. M. Atallah, and B. Khan, (2021) “Optimal power flow solution based on jellyfish search optimization considering uncertainty of renewable energy sources" IEEE Access 9: 100911–100933. DOI: https: //doi.org/10.1109/ACCESS.2021.3097006.
[35] V. Hayyolalam and A. A. P. Kazem, (2020) “Black widow optimization algorithm: a novel meta-heuristic approach for solving engineering optimization problems" Engineering Applications of Artificial Intelligence 87: 103249. DOI: https: //doi.org/10.1016/j.engappai.2019.103249.
[36] E. H. Houssein, B .E. -d. Helmy, D. Oliva, A. A. Elngar, and H. Shaban, (2021) “A novel black widow optimization algorithm for multilevel thresholding image segmentation" Expert Systems with Applications 167: 114159. DOI: https: //doi.org/10.1016/j.eswa.2020.114159.
[37] S. Memar, A. Mahdavi-Meymand, and W. Sulisz, (2021) “Prediction of seasonal maximum wave height for unevenly spaced time series by Black Widow Optimization algorithm" Marine Structures 78: 103005. DOI: https: //doi.org/10.1016/j.marstruc.2021.103005.

Latest Articles